1

    agensi-skill-authoring-with-codex

    by Markus Isaksson

    Turn your workflows and prompts into standardized, marketplace-ready Agensi skills and Codex-compatible folders.

    Updated May 2026
    0 installs

    Free

    One-time purchase

    Included in download

    • Downloadable skill package
    • Works with openai.yaml`.
    • 3 permissions declared
    • Instant install

    Sample Output

    A real example of what this skill produces.

    Skill Authoring Result

    Skill Folder: skills/code-reviewer Files: SKILL.md, agents/openai.yaml Positioning: Entry-tier paid utility for junior devs. Next Step: Run 'quick_validate.py' to ensure description length is within the 160-character Codex limit.

    About This Skill

    What it does

    This skill transforms rough ideas, chaotic workflows, or one-off prompts into professional-grade, Codex-compatible Agensi skills. It handles the heavy lifting of structuring your AI expertise into a reusable product, ensuring your skill folders follow the two-layer standard: agent-facing instructions in SKILL.md and UI-facing metadata in agents/openai.yaml.

    Why use this skill

    Writing a great skill requires more than just a good prompt; it requires clear trigger conditions, guardrails, and structured operating procedures. This skill acts as a senior technical writer for your AI agents, ensuring every skill you build is discoverable by the Codex orchestrator and ready for the Agensi marketplace. It prevents common mistakes like bloating frontmatter or providing vague instructions that lead to hallucination.

    Key Features

    • Two-Layer Architecture: Automatically separates system instructions from UI metadata.
    • Trigger Optimization: Writes rich frontmatter descriptions to ensure your skill is called at the right time.
    • Contract-First Design: Forces the creation of concrete output templates for predictable agent behavior.
    • Multi-Format Support: Ports existing prompts from Claude, Cursor, or Grok into the standardized Agensi format.
    • Validation Ready: Prepares folders for Codex validation scripts and marketplace publishing.

    Use Cases

    • Convert existing one-off prompts into reusable skill folders
    • Structure complex multi-phase workflows into agent-ready instructions
    • Generate OpenAI-specific metadata for better skill discovery in Codex
    • Standardize skill sets for team-wide distribution or marketplace sale

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Read Files
    Write Files
    Terminal / Shell

    File Scopes

    **/SKILL.md
    **/agents/openai.yaml
    **/*.md
    codex/agensi/**
    .codex/skills/**

    **Permission Profile:** Read + Write documentation

    Tags

    skill-authoring
    codex
    agensi
    prompt-engineering
    automation

    This skill is optimized for OpenAI Codex skill folders and Agensi product publishing. It can author portable Agensi skills, but Codex-specific UI metadata belongs in `agents/openai.yaml`.

    Creator

    Markus Isaksson

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    skill-router-2

    Automatically detect, load, and stack the perfect skills combo for any user request.

    $53 installs

    cinematic-sites

    Turn any basic business URL into a high-end cinematic landing page with AI-generated 4K assets and GSAP animations.

    $122 installs

    designing-hybrid-context-layers

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    $1012 installs

    diagnosing-rag-failure-modes

    RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

    $105 installs

    Free